[go: up one dir, main page]

CN113541747A - Large-scale MIMO detection method, device and storage medium - Google Patents

Large-scale MIMO detection method, device and storage medium Download PDF

Info

Publication number
CN113541747A
CN113541747A CN202110748205.8A CN202110748205A CN113541747A CN 113541747 A CN113541747 A CN 113541747A CN 202110748205 A CN202110748205 A CN 202110748205A CN 113541747 A CN113541747 A CN 113541747A
Authority
CN
China
Prior art keywords
layer
network
approximate
propagation network
cavity edge
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN202110748205.8A
Other languages
Chinese (zh)
Other versions
CN113541747B (en
Inventor
张川
葛荧萌
谈晓思
冀贞昊
张在琛
尤肖虎
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Zijinshan Laboratory
Southeast University
Original Assignee
Southeast University
Network Communication and Security Zijinshan Laboratory
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Southeast University, Network Communication and Security Zijinshan Laboratory filed Critical Southeast University
Priority to CN202110748205.8A priority Critical patent/CN113541747B/en
Publication of CN113541747A publication Critical patent/CN113541747A/en
Application granted granted Critical
Publication of CN113541747B publication Critical patent/CN113541747B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04B—TRANSMISSION
    • H04B7/00—Radio transmission systems, i.e. using radiation field
    • H04B7/02—Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas
    • H04B7/04—Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas using two or more spaced independent antennas
    • H04B7/0413—MIMO systems
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04B—TRANSMISSION
    • H04B17/00—Monitoring; Testing
    • H04B17/30—Monitoring; Testing of propagation channels
    • H04B17/309—Measuring or estimating channel quality parameters
    • H04B17/336—Signal-to-interference ratio [SIR] or carrier-to-interference ratio [CIR]
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04B—TRANSMISSION
    • H04B17/00—Monitoring; Testing
    • H04B17/30—Monitoring; Testing of propagation channels
    • H04B17/391—Modelling the propagation channel
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04B—TRANSMISSION
    • H04B7/00—Radio transmission systems, i.e. using radiation field
    • H04B7/02—Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas
    • H04B7/04—Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas using two or more spaced independent antennas
    • H04B7/08—Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas using two or more spaced independent antennas at the receiving station
    • H04B7/0837—Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas using two or more spaced independent antennas at the receiving station using pre-detection combining
    • H04B7/0842—Weighted combining
    • H04B7/0848—Joint weighting
    • H04B7/0854—Joint weighting using error minimizing algorithms, e.g. minimum mean squared error [MMSE], "cross-correlation" or matrix inversion
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
    • Y02D30/00—Reducing energy consumption in communication networks
    • Y02D30/70—Reducing energy consumption in communication networks in wireless communication networks

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Physics & Mathematics (AREA)
  • Electromagnetism (AREA)
  • Mathematical Physics (AREA)
  • Quality & Reliability (AREA)
  • Radio Transmission System (AREA)

Abstract

本发明公开了一种大规模MIMO检测方法、装置和存储介质，包括：将接收信号矢量、信道矩阵以及噪声方差数据输入到经训练的近似期望传播网络模型中，得到发射信号的估计值；基于深度学习网络构建近似期望传播网络，近似期望传播网络的每一层对应于EPA算法的每个迭代过程；在每个网络层中引入可学习的线性纠正参数来纠正EPA算法中每次迭代时的未归一化的腔边缘分布的二阶项系数；近似期望传播网络的最后一层输出发送信号的最终估计值；对构建的所述近似期望传播网络进行训练，得到训练后的可学习的线性纠正参数，固定可学习的线性纠正参数即得到经训练的近似期望传播网络模型。本发明以较低的复杂度实现了更好的性能提升。

Figure 202110748205

The invention discloses a massive MIMO detection method, device and storage medium. The deep learning network constructs an approximate expected propagation network, and each layer of the approximate expected propagation network corresponds to each iterative process of the EPA algorithm; a learnable linear correction parameter is introduced in each network layer to correct the EPA algorithm in each iteration. The coefficients of the second-order term of the unnormalized cavity edge distribution; the final estimated value of the output transmission signal of the last layer of the approximate expected propagation network; the constructed approximate expected propagation network is trained to obtain a learnable linear Correct the parameters, and fix the learnable linear correction parameters to obtain the trained approximate expectation propagation network model. The present invention achieves better performance improvement with lower complexity.

Figure 202110748205

Description

Large-scale MIMO detection method, device and storage medium
Technical Field
The invention belongs to the technical field of signal detection, and particularly relates to a large-scale MIMO detection method, a large-scale MIMO detection device and a large-scale MIMO detection storage medium.
Background
With the development of wireless communication technology, the number of mobile users is rapidly increasing, and higher requirements are put forward on the mobile communication technology, and problems such as the shortage of exposed spectrum resources and the utilization rate of low frequency spectrum are in urgent need to be solved. In addition, the fifth generation mobile communication (5G) network is gradually spread, and the requirements of high speed, high coverage, low power consumption, low time delay and the like further pose greater challenges to communication technology.
Large-scale multiple-input multiple-output (M-MIMO) systems have attracted a lot of attention from the industrial and academic circles due to their potentially high channel capacity, high speed and high spectrum utilization. Generally, a larger number of antennas may result in a larger channel capacity and a higher spectrum utilization rate for the communication system, but at the same time, the calculation complexity is too high, thereby increasing the implementation difficulty of the system. Optimal M-MIMO detection methods, such as the Maximum Likelihood (ML) or Maximum A Posteriori (MAP) algorithms, become unacceptable in M-MIMO systems due to their exponential complexity. In order to balance the complexity of hardware implementation and detection performance, a suboptimal detection method is generally adopted in an actual system, so that the suboptimal detection method can meet the requirement of lower complexity and maintain better performance.
In recent years, a Message Passing Algorithm (MPA) based on bayesian inference has been widely used in M-MIMO detection due to its excellent performance. The expected propagation algorithm (EP) proposed by C seeds in 2014 is one of the popular MPA, which shows excellent performance in various channel configurations. However, since EP requires matrix inversion for each iteration, and the computational complexity of matrix inversion is proportional to the cube of the number of antennas, the complexity is too high to be easily implemented in hardware in M-MIMO systems. Tan proposed an approximate Expected Propagation Algorithm (EPA) in 2019, which exhibits similar performance to the EP algorithm in independent co-distributed rayleigh channels and is much less complex. However, the channel correlation caused by the small M-MIMO antenna spacing is not negligible in a practical system, and the performance loss of the EPA detection method in the relevant channel is serious.
Deep Learning (DL) has been introduced and applied in recent years to assist M-MIMO detection to improve detection performance. M-MIMO detection methods based on deep learning are mainly divided into two main categories, including data-driven and model-driven methods. Although a certain result is achieved based on a data-driven method, the deep learning network is large in scale and requires a large amount of training cost; the M-MIMO detection method based on model driving has better performance and robustness by using the traditional physical model for reference. He proposes a deep learning network structure based on Orthogonal Approximate Message Passing (OAMP), called OAMPNet, which has better performance than the original OAMP detection performance, but has too high complexity in an M-MIMO system because of the need of performing matrix inversion operation in each layer of the network. Liao proposes a deep learning M-MIMO detection method (DLM) based on an Approximate Message Passing (AMP) algorithm, which has a serious performance loss in the relevant channels although it achieves better performance in independent and identically distributed rayleigh channels with lower complexity.
Disclosure of Invention
The purpose of the invention is as follows: aiming at the problems in the prior art, the invention discloses a large-scale MIMO detection method, a device and a storage medium, which solve the problem that the performance loss of the existing MIMO detection method based on the approximate expectation propagation algorithm is serious in related channels.
The technical scheme is as follows: in order to achieve the purpose, the invention adopts the following technical scheme: a large-scale MIMO detection method comprises the following steps:
obtaining a received signal vector, a channel matrix and a noise variance according to the obtained received signal, channel information and noise information;
inputting the received signal vector, the channel matrix and the noise variance data into a trained approximate expected propagation network model to obtain an estimated value of a transmitting signal;
the approximate expected propagation network model training process comprises:
constructing an approximate expected propagation network based on the deep learning network, wherein each layer of the approximate expected propagation network corresponds to each iterative process of the EPA algorithm; introducing learnable linear correction parameters at each network layer to correct second-order coefficient of non-normalized cavity edge distribution at each iteration in the EPA algorithm; outputting a final estimated value of a transmission signal by the last layer of the approximate expected propagation network;
training the constructed approximate expected propagation network to obtain learnable linear correction parameters after training, and fixing the learnable linear correction parameters to obtain the trained approximate expected propagation network model.
Further, a learnable damping coefficient is introduced in each network layer to correct the mean and variance of the cavity edge distribution at each iteration in the EPA algorithm.
Further, the input parameters approximating each layer of the desired propagation network include:
normalized Gram matrix
Figure BDA0003143735440000021
Normalized matched output
Figure BDA0003143735440000022
A first order term coefficient for an unnormalized cavity edge distribution of a current layer;
second order term coefficients for the non-normalized cavity edge distribution before the current layer linear correction;
and, the mean and variance of the cavity edge distribution output by the previous layer;
wherein y is a real-domain received signal vector, H is a real channel matrix,
Figure BDA0003143735440000031
is the noise variance.
Further, the output parameters of each layer of the approximate expected propagation network include:
the coefficient of the first order term for the un-normalized cavity edge distribution of the next layer, the estimate of the transmit signal output by the current layer, and the mean and variance of the cavity edge distribution output by the current layer.
Further, the total loss function approximating the desired propagation network is a weighted average of the partial loss functions of each network layer, the partial loss functions of each network layer being set to the estimated value of the transmitted signal and the minimum mean square error of the transmitted signal at the output of each network layer.
A massive MIMO detection apparatus comprising:
a training module for constructing an approximate expected propagation network based on the deep learning network, each layer of the approximate expected propagation network corresponding to each iterative process of the EPA algorithm; introducing learnable linear correction parameters at each network layer to correct second-order coefficient of non-normalized cavity edge distribution at each iteration in the EPA algorithm; outputting a final estimated value of a transmission signal by the last layer of the approximate expected propagation network; training the constructed approximate expected propagation network to obtain learnable linear correction parameters after training, and fixing the learnable linear correction parameters to obtain the trained approximate expected propagation network model;
the acquisition module is used for acquiring a received signal vector, a channel matrix and a noise variance according to the acquired received signal, channel information and noise information;
and the estimation module is used for inputting the received signal vector, the channel matrix and the noise variance data into the trained approximate expected propagation network model to obtain an estimation value of the transmitting signal.
Further, a learnable damping coefficient is introduced in each network layer to correct the mean and variance of the cavity edge distribution at each iteration in the EPA algorithm.
Further, the input parameters approximating each layer of the desired propagation network include:
normalized Gram matrix
Figure BDA0003143735440000032
Normalized matched output
Figure BDA0003143735440000033
A first order term coefficient for an unnormalized cavity edge distribution of a current layer;
second order term coefficients for the non-normalized cavity edge distribution before the current layer linear correction;
and, the mean and variance of the cavity edge distribution output by the previous layer;
wherein y is a real-domain received signal vector, H is a real channel matrix,
Figure BDA0003143735440000041
is the noise variance.
Further, the output parameters of each layer of the approximate expected propagation network include:
the coefficient of the first order term for the un-normalized cavity edge distribution of the next layer, the estimate of the transmit signal output by the current layer, and the mean and variance of the cavity edge distribution output by the current layer.
Further, the total loss function approximating the desired propagation network is a weighted average of the partial loss functions of each network layer, the partial loss functions of each network layer being set to the estimated value of the transmitted signal and the minimum mean square error of the transmitted signal at the output of each network layer.
A computer-readable storage medium storing computer-executable instructions for performing any of the massive MIMO detection methods described above.
Compared with the prior art, the invention has the following beneficial effects:
(1) the M-MIMO detection method based on the approximate expected propagation network (EPANet) model of the invention, each layer of the approximate expected propagation network corresponds to each iteration process of the EPA algorithm; a learnable linear correction parameter is introduced into each network layer to correct a second-order coefficient of unnormalized cavity edge distribution in each iteration of an EPA algorithm, so that the coefficient is more accurate under a relevant channel, and the performance of the EPA detection method is improved;
(2) a learnable damping coefficient is introduced into each network layer to correct the mean value and variance of the unnormalized cavity edge distribution in each iteration of the EPA algorithm, so that the performance of the algorithm is further improved, and the convergence stability of the algorithm is ensured;
(3) the partial loss function of each network layer is set as the minimum mean square error of the output and the sending signal of each network layer, and the total loss function of the network layers is set as the weighted average of the loss functions of each network layer, so that the convergence performance of the algorithm is improved;
experiments prove that the performance of the method in the related channel is obviously superior to that of the prior art, the complexity is low, and better performance improvement is realized with low complexity.
Drawings
FIG. 1 is a flow chart of a massive MIMO detection method according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of an EPANet network according to an embodiment of the present invention;
FIG. 3 is a schematic view of a detection apparatus according to an embodiment of the present invention;
FIG. 4 shows the correlation coefficient ζ of the EPANet detection method (only the learnable linear correction parameter is considered) and other detection methods in the embodiment of the present inventionr＝ζr0.3, different receiving and transmitting antenna conditionsIn the form, the BER is plotted against the SNR;
FIG. 5 shows the correlation coefficient ζ of the EPANet detection method (only the learnable linear correction parameter is considered) and other detection methods in the embodiment of the present inventionr＝ζrThe BER is plotted along with the change of the SNR under the condition of different receiving and transmitting antenna numbers which are 0.5;
FIG. 6 shows the correlation coefficient ζ of the EPANet detection method (considering learnable linear correction parameters and damping coefficients) and other detection methods in embodiments of the inventiont＝ζrThe BER is plotted along with the change of the SNR under the condition of different receiving and transmitting antenna numbers;
FIG. 7 shows the correlation coefficient ζ of the EPANet detection method (considering learnable linear correction parameters and damping coefficients) and other detection methods in embodiments of the inventiont＝ζrThe BER is plotted along with the change of the SNR under the condition of different receiving and transmitting antenna numbers which are 0.5;
fig. 8 is a graph showing the performance loss versus complexity for the EPANet detection method (considering learnable linear correction parameters and damping coefficients) and other detection methods in the embodiment of the present invention for 32 transmit antennas and 48 receive antennas.
Detailed Description
The present invention will be further described with reference to the accompanying drawings.
The M-MIMO system is set up as follows:
the user side is configured with Nt transmitting antennas, and the base station side is configured with NrRoot receiving antenna, wherein Nt＜Nr. The M-MIMO system is simplified into the following real number domain mathematical model:
y＝Hx+n (1)
wherein,
Figure BDA0003143735440000051
for real received signal vectors, where yjFor the j-th dimension received signal, j is 1, 2, …, 2Nr. Since the signals in the real system are all equivalent to complex numbers, the real part and the imaginary part of the complex numbers need to be considered when converting into a real number model, so that the y vector has 2N in totalrThe components (x, H and n are similar to each other) (. C)TIt is shown that the transpose operation,
Figure BDA0003143735440000052
transmitting a vector of signals for real numbers, wherein xiFor the ith dimension, i is 1, 2, …, 2NtH is 2Nr×2NtA real channel matrix of dimensions is formed,
Figure BDA0003143735440000053
is real additive white Gaussian noise, where njIs a j-th dimension real number noise signal, the noise mean value is 0, and the variance is
Figure BDA0003143735440000054
The channel in the invention mainly considers a Kronecker related channel model, and a channel matrix under the model can be expressed as follows:
H＝R1/2Hi.i.d.T1/2 (2)
wherein, R is receiving end space correlation matrix, T is sending end space correlation matrix, and its receiving end and sending end correlation usually use correlation coefficient ζ respectivelyrAnd ζtTo measure. R1/2And T1/2Can be obtained by Cholesky decomposition, Hi.i.d.Is an independent and equally distributed Rayleigh channel matrix.
Assuming that the receiving end knows the channel condition, the ith dimension sends signal xiHas a prior probability of
Figure BDA00031437354400000616
Wherein,
Figure BDA0003143735440000061
is an indicator function indicating if signal x is transmittediIn the modulation constellation set Θ, the function takes a value of 1, otherwise the function takes a value of 0. The a posteriori probability of the transmitted signal vector can be expressed as:
Figure BDA0003143735440000062
wherein,
Figure BDA0003143735440000063
denotes y obedient mean as Hx and covariance matrix as
Figure BDA0003143735440000064
Is distributed in a multi-dimensional gaussian manner,
Figure BDA0003143735440000065
represents 2Nr×2NrDimensional unit array due to
Figure BDA0003143735440000066
Is a non-Gaussian function, making it difficult to maximize the posterior probability, and the core idea of the EP algorithm is to transmit a signal x in the ith dimension subject to a Gaussian distributioniApproximate prior probability distribution of
Figure BDA0003143735440000067
To approximate p (x)i) Wherein, oc represents proportional to, λiAnd gammaiThe coefficients of the second and first order terms of the non-normalized approximated prior probability distribution in the ith dimension, respectively, the approximated posterior probability q (x) of the transmitted signal vector can be expressed as:
Figure BDA0003143735440000068
setting a vector
Figure BDA0003143735440000069
And
Figure BDA00031437354400000610
diag {. is used to return a diagonal matrix. The updating formula of the mean vector mu and the covariance matrix sigma of the approximate a posteriori probability q (x) is as follows,
Figure BDA00031437354400000611
Figure BDA00031437354400000612
wherein,
Figure BDA00031437354400000613
is a normalized Gram matrix of the signal to be normalized,
Figure BDA00031437354400000614
is the normalized matching output. The (γ, a) is updated in each iteration of the EP algorithm, thereby updating the mean vector μ and covariance matrix Σ of the approximated a posteriori probabilities q (x), which become more and more accurate during the iteration.
Before the iteration starts, an initial value gamma is seti0 and λi＝Es -1，EsRepresenting the average symbol energy. Calculating a cavity edge distribution (cavity marginal distribution) of the ith dimension, from an approximate posterior probability q (x) of the transmit signal xi in the ith dimensioni) Deleting the approximate prior probability distribution in the ith dimension to obtain:
Figure BDA00031437354400000615
wherein, ViAnd ρiCoefficients of a second order term and a first order term of the ith-dimension non-normalized cavity edge distribution respectively, and then the mean value t of the ith-dimension cavity edge distributioniSum variance
Figure BDA0003143735440000071
The calculation formula is as follows:
Figure BDA0003143735440000072
Figure BDA0003143735440000073
μiis q (x)i) I.e. the ith-dimension component, Σ, of μiiIs q (x)i) I.e. the (i, i) th component of the matrix sigma;
then signal x is sentiApproximate posterior probability q (x)i) Can be expressed as:
Figure BDA0003143735440000074
introducing a transmit signal x to a cavity edge profile of dimension iiThe prior probability of (a) can be used to obtain a refined distribution
Figure BDA0003143735440000075
The EPA algorithm finds the sum from the point of view of KL divergence (Kullback-Leibler divergence) minimum
Figure BDA0003143735440000076
Nearest q (x)i). Due to q (x)i) Is a Gaussian distribution, where minimizing KL divergence is equivalent to moment matching (moment matching), i.e., the first and second moments are equal, there is
Figure BDA0003143735440000077
Figure BDA0003143735440000078
Wherein eta isiIs a refining profile
Figure BDA0003143735440000079
I.e. the estimate of the ith-dimension transmitted signal xi,
Figure BDA00031437354400000710
for refining distribution
Figure BDA00031437354400000715
The average value of (a) of (b),
Figure BDA00031437354400000711
representing the transmitted signal xiObey mean value of tiVariance of
Figure BDA00031437354400000712
A gaussian distribution of (a). Order to
Figure BDA00031437354400000713
And
Figure BDA00031437354400000714
equation (11) can be equivalently expressed as:
ρ+γ＝(V+Λ)η (13)
substituting the formula (11) and the formula (13) into the formula (5) and the formula (6), according to the related documents (x.tan, y. -l.ueng, z.zhang, x.you, and c.zhang, "low-complex MIMO detection based on adaptive amplification processing," IEEE trans.veh.technol., vol.68, No.8, pp.7260-7272, aug.2019),:
ρ＝b+(-A+V)η (14)
at this point, sigma still needs to be calculated in each iterationiiThe EPA algorithm takes into account the characteristics of channel hardening in M-MIMO systems, i.e. the Gram matrix H when the number of antennas is particularly largeTH tends to a diagonal matrix, and the Gram matrix is replaced by the diagonal matrix formed by diagonal elements of the Gram matrix, so that the inversion at the moment becomes diagonal matrix inversion. Therefore, the temperature of the molten metal is controlled,
Figure BDA0003143735440000081
{HTH}iithe element value of the ith row and the ith column of the Gram matrix;
according to formula (12) have
Figure BDA0003143735440000082
It can be seen that the EPA algorithm works approximately if the Gram matrix is approximately diagonal, and the diagonal dominance of the Gram matrix in the relevant channel is no longer obvious, so the performance of the EPA deteriorates drastically.
Therefore, the scheme of the present invention is proposed to solve the problem that the performance of the existing EPA algorithm deteriorates drastically under the relevant channel.
Example 1:
as shown in fig. 1, a massive MIMO detection method includes the steps of:
step 101, constructing an approximate expected propagation network based on a deep learning network, introducing learnable linear correction parameters, and training to obtain a trained approximate expected propagation network model;
102, obtaining a received signal vector y, a channel matrix H and a noise variance according to the obtained received signal, channel information and noise information
Figure BDA0003143735440000083
Step 103, receiving the signal vector y, the channel matrix H and the noise variance
Figure BDA0003143735440000084
The data is input into a trained approximate expected propagation network model to obtain an estimated value of the transmitted signal.
Preferably, the approximate expected propagation network model training method includes:
1) constructing an approximate expected propagation network based on the deep learning network, and marking the approximate expected propagation network as EPANet, wherein each layer of the approximate expected propagation network corresponds to each iteration process of the EPA algorithm as shown in FIG. 2; introducing learnable linear correction parameters in each network layer (the network layer referred to in this disclosure represents a layer that approximates the desired propagation network) to correct second order coefficients of the unnormalized cavity edge distribution at each iteration in the EPA algorithm; the output value of the last layer of the approximate expected propagation network is used as the final estimated value of the transmitted signal;
preferably, the input parameters of each layer (i.e. the ith layer) of the approximate expected propagation network include:
normalized Gram matrix
Figure BDA0003143735440000091
And normalized matched output
Figure BDA0003143735440000092
First order coefficient for ith dimension unnormalized cavity edge distribution of ith layer
Figure BDA0003143735440000093
Second order coefficient for ith dimension unnormalized cavity edge distribution before linear correction for ith layer
Figure BDA0003143735440000094
And, the mean of the cavity edge distribution of the ith dimension of the l-1 th layer output
Figure BDA0003143735440000095
Sum variance
Figure BDA0003143735440000096
Preferably, the output parameters of each layer (i.e. the ith layer) of the approximate expected propagation network include:
coefficient of first order term for ith dimension unnormalized cavity edge distribution of layer l +1 obtained by corrected EPA algorithm
Figure BDA0003143735440000097
Ith dimension transmission signal xiIs estimated value of
Figure BDA0003143735440000098
And cavity edge of ith dimension of ith layer outputMean value of distribution
Figure BDA0003143735440000099
Sum variance
Figure BDA00031437354400000910
2NtAn
Figure BDA00031437354400000911
Estimated value vector eta of transmission signal composing output of l-th layer(l)，2NtAn
Figure BDA00031437354400000912
Coefficient vector p constituting the first order term of the unnormalized cavity edge distribution for the next layer(l+1)。
The initial values of the input parameters are calculated as follows:
setting initial values of coefficients of a second order term and a first order term for the ith dimension non-normalized approximate prior probability distribution during initialization of the EPA algorithm
Figure BDA00031437354400000913
And
Figure BDA00031437354400000914
Esrepresenting the average symbol energy. Then, according to the formulas (5) and (6), calculating to obtain a mean value vector mu of the approximate posterior probability distribution of the sending signal vector when the EPA algorithm is initialized(0)Sum covariance matrix ∑(0)And then, calculating coefficients of a first order term and a second order term of the ith dimension non-normalized cavity edge distribution during initialization of the EPA algorithm according to the formula (11) and the formula (12)
Figure BDA00031437354400000915
And Vi (0)：
Figure BDA00031437354400000916
Figure BDA00031437354400000917
Wherein,
Figure BDA00031437354400000918
and
Figure BDA00031437354400000919
respectively sending the mean value and the variance of the approximate posterior probability distribution of the signal vector when the EPA algorithm is initialized; and for the first order term of the ith dimension unnormalized cavity edge distribution at the first iteration of the EPA algorithm
Figure BDA00031437354400000920
Each layer of the approximate expected propagation network corresponds to each iterative process of the EPA algorithm, introducing two learnable parameters α in each network layer(l)And beta(l)To linearly correct V at each iteration in the EPA algorithmi (l)(i.e., the second order coefficient of the i-th dimension non-normalized cavity edge distribution at the i-th iteration, equation (16), where the superscript L represents the number of the approximate expected propagation network layer, which is also the iteration number of the EPA algorithm, and ranges from 1, 2, …, L; L is the set number of the approximate expected propagation network layers, which is the set maximum number of iterations of the EPA algorithm)
Figure BDA0003143735440000101
After linear correction, it is recorded as Vi (l)Then V isi (l)The following expression is given:
Figure BDA0003143735440000102
wherein,
Figure BDA0003143735440000103
in view of Vi (l)Is q\i(xi) Must be greater than 0, so a ReLU activation function is added to further adjust Vi (l)Thus Vi (l)The final expression of (c) is:
Figure BDA0003143735440000104
where ε is a very small constant that avoids the variance becoming infinite, and takes the value of 1 × 10 in subsequent simulations-12。
By correcting the second-order term coefficient of the cavity edge distribution of which the ith dimension is not normalized during the ith iteration, the coefficient is more accurate under a relevant channel, and the performance of the EPA detection method is improved.
Calculating a cavity edge distribution q of the ith dimension of the ith layer by equations (8) and (9)(l)\i(xi) Mean value of
Figure BDA0003143735440000105
Sum variance
Figure BDA0003143735440000106
And substituting the average value into formula (11) to obtain the average value of the refined distribution of the first network layer
Figure BDA0003143735440000107
I.e. the ith dimension of the first iteration of the EPA algorithm sends signal xi2N, will betAn
Figure BDA0003143735440000108
Component vector eta(l)I.e. the estimated value of the transmitted signal vector at the l-th network layer; the coefficients of the first order terms of the non-normalized cavity edge distribution of the l +1 th layer are found according to equation (14):
Figure BDA0003143735440000109
2Ntan
Figure BDA00031437354400001010
Component vector rho(l+1)A, b, ρ(l+1)、
Figure BDA00031437354400001011
And
Figure BDA00031437354400001012
as input to the next network layer;
output value eta of Lth network layer(L)And is output as a final estimation value of the transmission signal.
Preferably, considering that the EPA iterative algorithm does not reach an optimal solution after many iterations if the convergence is too fast and easily diverges and too slow, and the iterative algorithm easily falls into a local optimal solution in the iteration process, in order to ensure the convergence stability of the algorithm and further improve the performance of the algorithm, the q is distributed to the cavity edge of the ith dimension of the ith layer(l)\i(xi) Mean value of
Figure BDA00031437354400001013
Sum variance
Figure BDA00031437354400001014
Introducing learnable damping coefficients
Figure BDA00031437354400001015
And
Figure BDA00031437354400001016
as will be shown below, in the following,
Figure BDA00031437354400001017
Figure BDA00031437354400001018
wherein, when l is 1,
Figure BDA00031437354400001019
take a value of
Figure BDA00031437354400001020
Figure BDA00031437354400001021
Take a value of
Figure BDA00031437354400001022
Figure BDA0003143735440000111
Figure BDA0003143735440000112
Substituting equations (19) and (20) into equation (11) to obtain the mean value of the refined distribution of the l-th network layer
Figure BDA0003143735440000113
I.e. the ith dimension of the first iteration of the EPA algorithm sends signal xi2N, will betAn
Figure BDA0003143735440000114
Component vector eta(l)I.e. the estimated value of the transmitted signal at the l-th network layer;
2) training the constructed approximate expected propagation network through training data to obtain a learnable parameter after training, and fixing the learnable parameter to obtain a trained approximate expected propagation network model;
the method specifically comprises the following steps: training the constructed approximate expected propagation network through training data to obtain a learnable parameter alpha after training(l)And beta(l)Fixing the learnable parameters to obtain a trained approximate expected propagation network model;
preferably, the approximation constructed by the training data pairs takes into account the introduction of a learnable damping coefficientTraining the expected propagation network to obtain a learnable parameter alpha after training(l)And beta(l)And a learnable damping coefficient
Figure BDA0003143735440000115
And
Figure BDA0003143735440000116
fixing learnable parameters and damping coefficients to obtain a trained approximate expected propagation network model;
training data and verification data are randomly generated under different channel configurations, and the method comprises the following steps: sending signal vector x, normalized Gram matrix
Figure BDA0003143735440000117
And normalized matched output
Figure BDA0003143735440000118
Preferably, the partial loss function of each network layer is set as the minimum mean square error of the estimated value of the transmission signal output by each network layer and the transmission signal (i.e. the training label), and the total loss function of the network layer is set as the weighted average of the loss functions of each network layer, so as to improve the convergence performance of the algorithm, and the total loss function of the network layer is:
Figure BDA0003143735440000119
wherein, wlIs the weight of the ith network layer.
The learning rate is set, batch training is used, and the minimum batch size, total training data and training iteration number are set. Selecting a specific optimizer (such as Adam) to train on a platform supporting machine learning, and optimizing parameter sets
Figure BDA0003143735440000121
Until a maximum number of training iterations is reached.
The order of steps 101 and 102 in this embodiment may be interchanged.
Example 2:
as shown in fig. 3, a massive MIMO detection apparatus includes:
the training module is used for training the approximate expected propagation network model, constructing the approximate expected propagation network based on the deep learning network, and each layer of the approximate expected propagation network corresponds to each iterative process of the EPA algorithm; introducing learnable linear correction parameters in each network layer to correct second-order coefficient of non-normalized cavity edge distribution at each iteration in the EPA algorithm; outputting a final estimated value of a transmission signal by the last layer of the approximate expected propagation network; training the constructed approximate expected propagation network to obtain learnable linear correction parameters after training, and fixing the learnable linear correction parameters to obtain a trained approximate expected propagation network model;
the acquisition module is used for acquiring a received signal vector, a channel matrix and a noise variance according to the acquired received signal, channel information and noise information;
and the estimation module is used for inputting the received signal vector, the channel matrix and the noise variance data into the trained approximate expected propagation network model to obtain an estimation value of the transmitting signal.
Preferably, the second order term coefficient of the unnormalized cavity edge distribution at each iteration in the corrected EPA algorithm is:
Figure BDA0003143735440000122
wherein,
Figure BDA0003143735440000123
second order term coefficients for the ith dimension unnormalized cavity edge distribution at the l iteration in the EPA algorithm before correction, { HTH}iiFor the value of the element in the ith row and ith column of the Gram matrix,
Figure BDA0003143735440000124
as a noise squarePoor, H is 2Nr×2NtReal channel matrix of dimension, NtFor the number of transmitting antennas, NrFor the number of receiving antennas, α(l)And beta(l)The linear correction parameters which can be learnt by the l layer are all the linear correction parameters; ReLU is an activation function, and epsilon is a set constant;
Figure BDA0003143735440000125
Figure BDA0003143735440000126
the variance of the approximate a posteriori probability distribution of the transmitted signal vector at initialization of the EPA algorithm,
Figure BDA0003143735440000127
the coefficients of the second order term that approximate the prior probability distribution are not normalized for the ith dimension at initialization of the EPA algorithm.
Preferably, a learnable damping coefficient is introduced into each network layer to correct the mean and variance of the cavity edge distribution at each iteration in the EPA algorithm, and the formula is:
Figure BDA0003143735440000128
Figure BDA0003143735440000131
wherein,
Figure BDA0003143735440000132
and
Figure BDA0003143735440000133
mean and variance of the cavity edge distribution in the ith dimension of the ith iteration in the EPA algorithm,
Figure BDA0003143735440000134
and
Figure BDA0003143735440000135
all the damping coefficients can be learned by the introduced l-th layer, when l is 1,
Figure BDA0003143735440000136
has a value of
Figure BDA0003143735440000137
Figure BDA0003143735440000138
Has a value of
Figure BDA0003143735440000139
Preferably, the input parameters of the l-th layer of the approximate expected propagation network include:
normalized Gram matrix
Figure BDA00031437354400001310
Normalized matched output
Figure BDA00031437354400001311
Coefficients for first order terms of ith-dimension unnormalized cavity edge distribution for ith layer
Figure BDA00031437354400001312
The initial values are:
Figure BDA00031437354400001313
second order coefficient for ith dimension unnormalized cavity edge distribution before linear correction for ith layer
Figure BDA00031437354400001314
The initial values are:
Figure BDA00031437354400001315
and, the mean of the cavity edge distribution of the ith dimension of the l-1 th layer output
Figure BDA00031437354400001316
Sum variance
Figure BDA00031437354400001317
The initial values are:
Figure BDA00031437354400001318
Figure BDA00031437354400001319
i＝1，2，…，2Nt
preferably, the output parameters of the l-th layer of the approximate expected propagation network include:
coefficient of first order term for ith dimension unnormalized cavity edge distribution of layer l +1 obtained by corrected EPA algorithm
Figure BDA00031437354400001320
Estimated value of ith dimension transmission signal xi
Figure BDA00031437354400001321
And average of the i-dimension cavity edge distribution of the l-th layer output
Figure BDA00031437354400001322
Sum variance
Figure BDA00031437354400001323
2NtAn
Figure BDA00031437354400001324
Estimated value vector eta of transmission signal composing output of l-th layer(l)，2NtAn
Figure BDA0003143735440000141
Coefficient vector p constituting the first order term of the unnormalized cavity edge distribution for the next layer(l+1)。
Wherein, the superscript L represents the sequence number of the approximate expected propagation network layer, the range of L is 1, 2, …, L is the total layer number of the set approximate expected propagation network,
Figure BDA0003143735440000142
and
Figure BDA0003143735440000143
respectively the mean and variance of the approximate a posteriori probability distribution of the transmitted signal vector at initialization of the EPA algorithm,
Figure BDA0003143735440000144
the coefficient of the first-order term of the ith dimension non-normalized approximate prior probability distribution when the EPA algorithm is initialized; y is a real received signal vector.
Preferably, the total loss function D (η, x) approximating the desired propagation network is:
Figure BDA0003143735440000145
wherein, wlIs the weight of the l network layer, xiFor the signal to be transmitted in the i-th dimension,
Figure BDA0003143735440000146
sending a signal x for the ith dimension of the first iteration of the EPA algorithmiAn estimate of (d).
Example 3:
a computer-readable storage medium storing computer-executable instructions for performing the massive MIMO detection method of any one of embodiments 1.
Example 4:
the present invention is configured as an example in such a way that a transmission signal vector x is uniformly and randomly generated from QPSK modulationThe channel matrix H is randomly generated from a correlation channel model, in which the correlation coefficient is ζt＝ξr0.3 or ζt＝ξrAnd (3) when the number of the transmitting antennas is 0.5, the number of the receiving antennas is 48 or 64, and the signal-to-noise ratio is randomly and uniformly selected from 0-16 dB. The learning rate was set to 0.001, batch training was used, the minimum batch size was set to 64, and the total training data size was 16000. 50 iterative training were performed by the Adam optimizer in the Pythrch platform, optimizing the parameter set { α }(l)，β(l)And f, until the maximum training iteration number is reached. The simulation results were analyzed as follows:
and (3) comparing the performances of EPANet, EP, EPA and other several deep learning-based methods (including OAMPNet and DLM) under different antenna ratios and correlation coefficients:
FIG. 4 shows the correlation coefficient ζt＝ζrWhen the BER (bit error rate) is plotted against the SNR (signal to noise ratio) for different numbers of transmit and receive antennas, it can be seen that EPANet has a certain improvement in performance compared to the EPA algorithm for 64 numbers of receive antennas, and is better than other machine learning-based detection methods and EP performance. In the case of 48 receiving antennas, the performance of the EPANet proposed by the present invention is significantly better than that of other detection methods. When coefficient of correlation ζt＝ζrAt 0.5, as shown in fig. 5, the EPA and several other machine learning based detection methods face severe performance loss. Although the EPANet algorithm performs less than EP, it still significantly improves the performance of EPA and outperforms several other machine learning based detection methods.
A learnable damping coefficient is further introduced into the large-scale MIMO detection method, and the optimization parameter set is trained according to the experimental method
Figure BDA0003143735440000151
Until a maximum number of training iterations is reached. The simulation results were analyzed as follows:
and (3) comparing the performances of EPANet, EP, EPA and other several deep learning-based methods (including OAMPNet and DLM) under different antenna ratios and correlation coefficients:
FIG. 6 shows the correlation coefficient ζt＝ζrThe BER (bit error rate) versus SNR (signal to noise ratio) curve for different numbers of transmit and receive antennas is 0.3, and it can be seen that the performance of EPANet is slightly improved compared with the EPA algorithm under the condition that the number of receive antennas is 64, mainly because the channel is close to the independent and identically distributed rayleigh channel under the configuration, and the performance of the EPA algorithm is close to the optimum. Nonetheless, EPANet's performance is superior to other machine learning based detection methods and superior to EP's performance. In the case of 48 receiving antennas, the performance of the EPANet proposed by the present invention is significantly better than that of other detection methods. When coefficient of correlation ζt＝ζrAt 0.5, as shown in fig. 7, the EPA and several other machine learning based detection methods face severe performance loss. Although the EPANet algorithm performs less than EP, it still significantly improves the performance of EPA and outperforms several other machine learning based detection methods. At this time and in FIG. 5 only the set of optimization parameters { α }(l)，β(l)Comparing the performances of the two groups, it can be seen that the parameter set is added
Figure BDA0003143735440000152
The performance is further improved and is greatly superior to the EPA algorithm and other detection methods based on machine learning.
Performance loss versus complexity for different correlation channel cases:
the EPANet network model on the abscissa in FIG. 8 is obtaining a bit error rate BER of 10-3SNR loss compared to the EP algorithm, on the ordinate, of
Figure BDA0003143735440000153
For measuring the relative complexity of the algorithm, wherein
Figure BDA0003143735440000154
Indicating the complexity of some M-MIMO detection method,
Figure BDA0003143735440000155
indicating MMSThe complexity of the E detection method (minimum mean square error M-MIMO detection method), the calculation of which takes into account the floating-point number operations of exponential, multiplication, division and addition operations. The FTR represents the failure of the detection method to achieve a specified BER within the illustrated SNR. The two ends of the arrow represent the correlation coefficient xi respectivelyt＝ζr0.3 and xit＝ζr0.5. EPANet Performance at ζt＝ξrThe case of 0.3 is superior to EP, although ζ is superiort＝ζrPerformance was weaker than EP at 0.5, but EPANet complexity was only 44.36% of EP. EPANet has similar complexity to EPA, and better performance can be obtained under different channel configurations. In addition, compared with OAMPNet, the complexity of EPANet is reduced by 70%, and the performance is improved by 0.8-1.1 dB. While DLM is the lowest in complexity, it is when the channel correlation is strong, i.e.. zetat＝ξrAt 0.5, its performance is severely degraded and even fails to converge. The robustness of EPANet to different channel correlations is verified by the change in SNR loss (EPANet arrow length shortest).
The above description is only of the preferred embodiments of the present invention, and it should be noted that: it will be apparent to those skilled in the art that various modifications and adaptations can be made without departing from the principles of the invention and these are intended to be within the scope of the invention.

Claims (11)

1.一种大规模MIMO检测方法，其特征在于：包括步骤：1. a massive MIMO detection method, is characterized in that: comprise the steps: 根据获取的接收信号、信道信息和噪声信息得到接收信号矢量、信道矩阵以及噪声方差；Obtain the received signal vector, channel matrix and noise variance according to the acquired received signal, channel information and noise information; 将接收信号矢量、信道矩阵以及噪声方差数据输入到经训练的近似期望传播网络模型中，得到发射信号的估计值；Input the received signal vector, channel matrix and noise variance data into the trained approximate expected propagation network model to obtain the estimated value of the transmitted signal; 所述近似期望传播网络模型训练过程包括：The training process of the approximate expectation propagation network model includes: 基于深度学习网络构建近似期望传播网络，近似期望传播网络的每一层对应于EPA算法的每个迭代过程；在每个网络层引入可学习的线性纠正参数来纠正EPA算法中每次迭代时的未归一化的腔边缘分布的二阶项系数；近似期望传播网络的最后一层输出发送信号的最终估计值；The approximate expectation propagation network is constructed based on the deep learning network, and each layer of the approximate expectation propagation network corresponds to each iterative process of the EPA algorithm; a learnable linear correction parameter is introduced in each network layer to correct the EPA algorithm in each iteration. The coefficients of the second-order term of the unnormalized cavity edge distribution; approximate the final estimate of the output transmitted signal of the last layer of the desired propagation network; 对构建的所述近似期望传播网络进行训练，得到训练后的可学习的线性纠正参数，固定可学习的线性纠正参数即得到所述经训练的近似期望传播网络模型。The constructed approximate expectation propagation network is trained to obtain learnable linear correction parameters after training, and the trained approximate expectation propagation network model is obtained by fixing the learnable linear correction parameters. 2.根据权利要求1所述的一种大规模MIMO检测方法，其特征在于：在每个网络层中引入可学习的阻尼系数来纠正EPA算法中每次迭代时的腔边缘分布的均值和方差。2. A kind of massive MIMO detection method according to claim 1 is characterized in that: in each network layer, a learnable damping coefficient is introduced to correct the mean value and variance of the cavity edge distribution during each iteration in the EPA algorithm . 3.根据权利要求1所述的一种大规模MIMO检测方法，其特征在于：所述近似期望传播网络的每一层的输入参数包括：3. A massive MIMO detection method according to claim 1, wherein the input parameters of each layer of the approximate desired propagation network comprise: 归一化后的Gram矩阵
Figure FDA0003143735430000011
Normalized Gram matrix
Figure FDA0003143735430000011
 归一化后的匹配输出
Figure FDA0003143735430000012
Normalized matching output
Figure FDA0003143735430000012
 用于当前层的未归一化的腔边缘分布的一阶项系数；coefficients of the first-order term for the unnormalized cavity edge distribution of the current layer; 用于当前层线性纠正前的未归一化的腔边缘分布的二阶项系数；coefficients of the second-order term for the unnormalized cavity edge distribution before the linear correction of the current layer; 以及上一层输出的腔边缘分布的均值和方差；and the mean and variance of the cavity edge distribution output by the previous layer; 其中，y为实数域接收信号矢量，H为实数信道矩阵，
Figure FDA0003143735430000013
为噪声方差。Among them, y is the received signal vector in the real number domain, H is the real number channel matrix,
Figure FDA0003143735430000013
is the noise variance. 4.根据权利要求1所述的一种大规模MIMO检测方法，其特征在于：所述近似期望传播网络的每一层的输出参数包括：4. A massive MIMO detection method according to claim 1, wherein the output parameters of each layer of the approximate desired propagation network comprise: 用于下一层的未归一化的腔边缘分布的一阶项的系数，当前层输出的发送信号的估计值，以及当前层输出的腔边缘分布的均值和方差。Coefficients for the first-order term of the unnormalized cavity edge distribution of the next layer, an estimate of the transmit signal output by the current layer, and the mean and variance of the cavity edge distribution output by the current layer. 5.根据权利要求1～4任意一项所述的一种大规模MIMO检测方法，其特征在于：所述近似期望传播网络的总的损失函数为每个网络层的部分损失函数的加权平均，每个网络层的部分损失函数设置为每个网络层的输出的发送信号估计值和发送信号的最小均方误差。5. The massive MIMO detection method according to any one of claims 1 to 4, wherein the total loss function of the approximate desired propagation network is the weighted average of the partial loss functions of each network layer, The partial loss function for each network layer is set as the transmitted signal estimate and the minimum mean square error of the transmitted signal at the output of each network layer. 6.一种大规模MIMO检测装置，其特征在于：包括：6. A massive MIMO detection device, characterized in that: comprising: 训练模块，用于基于深度学习网络构建近似期望传播网络，近似期望传播网络的每一层对应于EPA算法的每个迭代过程；在每个网络层引入可学习的线性纠正参数来纠正EPA算法中每次迭代时的未归一化的腔边缘分布的二阶项系数；近似期望传播网络的最后一层输出发送信号的最终估计值；对构建的所述近似期望传播网络进行训练，得到训练后的可学习的线性纠正参数，固定可学习的线性纠正参数即得到经训练的近似期望传播网络模型；The training module is used to construct an approximate expectation propagation network based on the deep learning network, and each layer of the approximate expectation propagation network corresponds to each iterative process of the EPA algorithm; learnable linear correction parameters are introduced in each network layer to correct the EPA algorithm. The coefficients of the second-order term of the unnormalized cavity edge distribution at each iteration; the final estimated value of the output transmission signal of the last layer of the approximate expected propagation network; the constructed approximate expected propagation network is trained, and the trained The learnable linear correction parameters are fixed, and the trained approximate expected propagation network model is obtained by fixing the learnable linear correction parameters; 获取模块，用于根据获取的接收信号、信道信息和噪声信息得到接收信号矢量、信道矩阵以及噪声方差；an acquisition module, configured to obtain the received signal vector, the channel matrix and the noise variance according to the acquired received signal, channel information and noise information; 估计模块，用于将接收信号矢量、信道矩阵以及噪声方差数据输入到经训练的近似期望传播网络模型中，得到发射信号的估计值。The estimation module is used for inputting the received signal vector, channel matrix and noise variance data into the trained approximate expected propagation network model to obtain the estimated value of the transmitted signal. 7.根据权利要求6所述的一种大规模MIMO检测装置，其特征在于：在每个网络层中引入可学习的阻尼系数来纠正EPA算法中每次迭代时的腔边缘分布的均值和方差。7. A massive MIMO detection device according to claim 6, characterized in that: a learnable damping coefficient is introduced in each network layer to correct the mean and variance of the cavity edge distribution during each iteration in the EPA algorithm . 8.根据权利要求6所述的一种大规模MIMO检测装置，其特征在于：所述近似期望传播网络的每一层的输入参数包括：8. A massive MIMO detection apparatus according to claim 6, wherein the input parameters of each layer of the approximate desired propagation network comprise: 归一化后的Gram矩阵
Figure FDA0003143735430000021
Normalized Gram matrix
Figure FDA0003143735430000021
 归一化后的匹配输出
Figure FDA0003143735430000022
Normalized matching output
Figure FDA0003143735430000022
 用于当前层的未归一化的腔边缘分布的一阶项系数；coefficients of the first-order term for the unnormalized cavity edge distribution of the current layer; 用于当前层线性纠正前的未归一化的腔边缘分布的二阶项系数；coefficients of the second-order term for the unnormalized cavity edge distribution before the linear correction of the current layer; 以及上一层输出的腔边缘分布的均值和方差；and the mean and variance of the cavity edge distribution output by the previous layer; 其中，y为实数域接收信号矢量，H为实数信道矩阵，
Figure FDA0003143735430000023
为噪声方差。Among them, y is the received signal vector in the real number domain, H is the real number channel matrix,
Figure FDA0003143735430000023
is the noise variance. 9.根据权利要求6所述的一种大规模MIMO检测装置，其特征在于：所述近似期望传播网络的每一层的输出参数包括：9. The massive MIMO detection apparatus according to claim 6, wherein the output parameters of each layer of the approximate desired propagation network comprise: 用于下一层的未归一化的腔边缘分布的一阶项的系数，当前层输出的发送信号的估计值，以及当前层输出的腔边缘分布的均值和方差。Coefficients for the first-order term of the unnormalized cavity edge distribution of the next layer, an estimate of the transmit signal output by the current layer, and the mean and variance of the cavity edge distribution output by the current layer. 10.根据权利要求6～9任意一项所述的一种大规模MIMO检测装置，其特征在于：所述近似期望传播网络的总的损失函数为每个网络层的部分损失函数的加权平均，每个网络层的部分损失函数设置为每个网络层的输出的发送信号的估计值和发送信号的最小均方误差。10. The massive MIMO detection device according to any one of claims 6 to 9, wherein the total loss function of the approximate desired propagation network is a weighted average of partial loss functions of each network layer, The partial loss function of each network layer is set as the estimated value of the transmitted signal and the minimum mean square error of the transmitted signal at the output of each network layer. 11.一种计算机可读存储介质，其特征在于，存储有计算机可执行指令，所述计算机可执行指令用于执行权利要求1～5中任意一项所述大规模MIMO检测方法。11 . A computer-readable storage medium, wherein computer-executable instructions are stored, and the computer-executable instructions are used to execute the massive MIMO detection method according to any one of claims 1 to 5 .
CN202110748205.8A 2021-07-01 2021-07-01 Large-scale MIMO detection method, device and storage medium Active CN113541747B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110748205.8A CN113541747B (en) 2021-07-01 2021-07-01 Large-scale MIMO detection method, device and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110748205.8A CN113541747B (en) 2021-07-01 2021-07-01 Large-scale MIMO detection method, device and storage medium

Publications (2)

Publication Number Publication Date
CN113541747A true CN113541747A (en) 2021-10-22
CN113541747B CN113541747B (en) 2022-07-08

Family

ID=78097637

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110748205.8A Active CN113541747B (en) 2021-07-01 2021-07-01 Large-scale MIMO detection method, device and storage medium

Country Status (1)

Country Link
CN (1) CN113541747B (en)

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114499601A (en) * 2021-12-23 2022-05-13 西安电子科技大学 Large-scale MIMO signal detection method based on deep learning
CN115276729A (en) * 2022-07-21 2022-11-01 南京大学 Signal detection method and system for large-scale MIMO system
CN115801500A (en) * 2022-10-10 2023-03-14 哈尔滨工程大学 High-order large-scale MIMO signal detection method
CN116489051A (en) * 2023-05-12 2023-07-25 南京邮电大学 A method, device, electronic equipment and storage medium for detecting and optimizing desired propagation signals
CN119807878A (en) * 2024-12-19 2025-04-11 北京航空航天大学 A low-complexity deep learning MIMO detection method based on partial MAP

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20140146925A1 (en) * 2012-11-27 2014-05-29 Samsung Electronics Co., Ltd. Method and apparatus for iteratively detecting and decoding signal in communication system with multiple-input and multiple-out (mimo) channel
US20180227217A1 (en) * 2015-07-31 2018-08-09 At&T Intellectual Property I, L.P. Method and apparatus for authentication and identity management of communicating devices
CN108390705A (en) * 2018-03-29 2018-08-10 东南大学 The extensive mimo system detection method of deep neural network based on BP algorithm structure
CN110719239A (en) * 2019-09-29 2020-01-21 东南大学 Data model dual-drive combined MIMO channel estimation and signal detection method
CN110740005A (en) * 2019-10-25 2020-01-31 网络通信与安全紫金山实验室 An uplink channel prediction method and prediction system based on path division multiple access

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20140146925A1 (en) * 2012-11-27 2014-05-29 Samsung Electronics Co., Ltd. Method and apparatus for iteratively detecting and decoding signal in communication system with multiple-input and multiple-out (mimo) channel
US20180227217A1 (en) * 2015-07-31 2018-08-09 At&T Intellectual Property I, L.P. Method and apparatus for authentication and identity management of communicating devices
CN108390705A (en) * 2018-03-29 2018-08-10 东南大学 The extensive mimo system detection method of deep neural network based on BP algorithm structure
CN110719239A (en) * 2019-09-29 2020-01-21 东南大学 Data model dual-drive combined MIMO channel estimation and signal detection method
CN110740005A (en) * 2019-10-25 2020-01-31 网络通信与安全紫金山实验室 An uplink channel prediction method and prediction system based on path division multiple access

Non-Patent Citations (3)

* Cited by examiner, † Cited by third party
Title
KHAC-HOANG NGO 等: "Non-Coherent Multi-User Detection Based on Expectation Propagation", 《2019 53RD ASILOMAR CONFERENCE ON SIGNALS, SYSTEMS, AND COMPUTERS》 *
XIAOSI TAN 等: "A Low-Complexity Massive MIMO Detection Based on Approximate Expectation Propagation", 《IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY》 *
XIAOSI TAN 等: "Improving Massive MIMO Message Passing Detectors With Deep Neural Network", 《IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY》 *

Cited By (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114499601A (en) * 2021-12-23 2022-05-13 西安电子科技大学 Large-scale MIMO signal detection method based on deep learning
CN114499601B (en) * 2021-12-23 2023-04-28 西安电子科技大学 Large-scale MIMO signal detection method based on deep learning
CN115276729A (en) * 2022-07-21 2022-11-01 南京大学 Signal detection method and system for large-scale MIMO system
CN115801500A (en) * 2022-10-10 2023-03-14 哈尔滨工程大学 High-order large-scale MIMO signal detection method
CN115801500B (en) * 2022-10-10 2024-06-18 哈尔滨工程大学 A high-order massive MIMO signal detection method
CN116489051A (en) * 2023-05-12 2023-07-25 南京邮电大学 A method, device, electronic equipment and storage medium for detecting and optimizing desired propagation signals
CN119807878A (en) * 2024-12-19 2025-04-11 北京航空航天大学 A low-complexity deep learning MIMO detection method based on partial MAP

Also Published As

Publication number Publication date
CN113541747B (en) 2022-07-08

Similar Documents

Publication Publication Date Title
CN113541747A (en) Large-scale MIMO detection method, device and storage medium
CN114051701B (en) Device and method for machine learning assisted precoding
CN111131097B (en) Block Diagonal Sparse Bayesian Channel Estimation Method in SC-MIMO Underwater Acoustic Communication Environment
CN113381952B (en) Multi-antenna system channel estimation method based on deep learning
CN112637094A (en) Multi-user MIMO receiving method based on model-driven deep learning
JP7762357B2 (en) Radio receiving device and method
CN109474388A (en) Signal detection method for low-complexity MIMO-NOMA system based on improved gradient projection method
CN115996078B (en) Two-stage beam forming method based on combined multi-arm gambling machine
JP2022163465A (en) Receiving device and parameter generation method for demodulation
CN118041401A (en) MIMO signal detection method, device, electronic device and storage medium
CN113630160B (en) Large-scale MIMO detection method, device, equipment and storage medium
CN110784274B (en) Method for determining receiver algorithm for large-scale multiple-input multiple-output
CN115865155B (en) A two-stage precoding method based on MAB in multi-scattering cluster channel
CN115037339B (en) Signal detection method and terminal equipment
CN118019047A (en) Multi-user access identification and detection method based on frequency domain pre-equalization in time-sensitive networks
CN118054992A (en) A low-complexity multi-input multi-output deep-sea channel estimation method and underwater acoustic communication system
US11309991B2 (en) Wireless receiver apparatus
CN103841067B (en) Equilibrium method of communication signals of underwater acoustic channel
CN117060952A (en) Signal detection method and device in multiple input multiple output system
CN119602838B (en) A system complexity optimization method for low-altitude massive MIMO fusion networks
CN107888537B (en) A Signal Detection Method to Improve System Complexity in Large-Scale Antenna Systems
CN117978219B (en) Precoding matrix generation method and device for large-scale MIMO system
Maki et al. A From-Scratch Approach to Deep Unfolding-Aided Bilinear Gaussian Belief Propagation for Correlated Large MIMO
CN112260811B (en) Pilot frequency distribution method of multi-input multi-output orthogonal frequency division multiplexing system
CN119341867A (en) A joint channel and data estimation method based on deconvolution

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant
CP03 Change of name, title or address
CP03 Change of name, title or address

Address after: No. 9 Mozhou East Road, Nanjing City, Jiangsu Province, 211111

Patentee after: Zijinshan Laboratory

Country or region after: China

Patentee after: SOUTHEAST University

Address before: No. 9 Mozhou East Road, Jiangning Economic Development Zone, Jiangning District, Nanjing City, Jiangsu Province

Patentee before: Purple Mountain Laboratories

Country or region before: China

Patentee before: SOUTHEAST University